Machine Learning and Formal Concept Analysis

  • Sergei O. Kuznetsov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2961)

Abstract

A model of learning from positive and negative examples is naturally described in terms of Formal Concept Analysis (FCA). In these terms, result of learning consists of two sets of intents (closed subsets of attributes): the first one contains intents that have only positive examples in the corresponding extents. The second one contains intents such that the corresponding extents contain only negative examples. On the one hand, we show how the means of FCA allows one to realize learning in this model with various data representation, from standard object-attribute one to that with labeled graphs. On the other hand, we use the language of FCA to give natural descriptions of some standard models of Machine Learning such as version spaces and decision trees. This allows one to compare several machine learning approaches, as well as to employ some standard techniques of FCA in the domain of machine learning. Algorithmic issues of learning with concept lattices are discussed. We consider applications of the concept-based learning, including Structure-Activity Relationship problem (in predictive toxicology) and spam filtering.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agrawal, R., Mannila, H., Srikant, R., Toivonen, H., Verkamo, A.I.: Fast Discovery of Association Rules. In: Advances in Knowledge Discovery and Data Mining, pp. 307–328 (1996)Google Scholar
  2. 2.
    Baader, F., Molitor, R.: Building and Structuring Description Logic Knowledge Spaces Using Least Common Subsumers and Concept Analysis. In: Ganter, B., Mineau, G.W. (eds.) ICCS 2000. LNCS (LNAI), vol. 1867, pp. 292–305. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  3. 3.
    Bahler, D., Bristol, D.W.: The induction of rules for predicting chemical cancerogenesis in rodents. In: Hunter, L., Searls, D., Shavlik, J. (eds.) Intelligent Systems for Molecular Biology, pp. 29–37. AAAI/MIT Press, Menlo Park, CA (1993)Google Scholar
  4. 4.
    Blinova, V.G.: Results of Application of the JSM-method of Hypothesis Generation to Problems of Analyzing the Relation “Structure of a Chemical Compound - Biological Activity”. Autom. Docum. Math. Ling. 29(3), 26–33 (1995)MathSciNetGoogle Scholar
  5. 5.
    Blinova, V.G., Dobrynin, D.A., Finn, V.K., Kuznetsov, S.O., Pankratova, E.S.: Toxicology analysis by means of the JSM-method. Bioinformatics 19, 1201–1207 (2003)CrossRefGoogle Scholar
  6. 6.
    Botta, M., Giordana, A., Saitta, L., Sebag, M.: Relational Learning as Search in a Critical Region. Journal of Machine Learning Research 4, 431–463 (2003)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Budunova, A.P., Poroikov, V.V., Blinova, V.G., Finn, V.K.: The JSM-method of hypothesis generation: Application for analysis of the relation “Structure - hepatoprotective detoxifying activity”. Nauchno-Tekhnicheskaya Informatsiya (7), 12–15 (1993) (in Russian)Google Scholar
  8. 8.
    Carpineto, C., Romano, G.: A Lattice Conceptual Clustering System and Its Application to Browsing Retrieval. Machine Learning 24, 95–122 (1996)Google Scholar
  9. 9.
    Chaudron, L., Maille, N.: Generalized Formal Concept Analysis. In: Ganter, B., Mineau, G.W. (eds.) ICCS 2000. LNCS, vol. 1867, pp. 357–370. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  10. 10.
    Data Mining Cup (DMC), http://www.data-mining-cup.de
  11. 11.
    Dehaspe, L., De Raedt, L.: Mining Association Rules in Multiple Relations. In: Džeroski, S., Lavrač, N. (eds.) ILP 1997. LNCS (LNAI), vol. 1297, pp. 125–132. Springer, Heidelberg (1997)Google Scholar
  12. 12.
    De Raedt, L., van Laer, W.: Inductive Constraint Logic. In: Zeugmann, T., Shinohara, T., Jantke, K.P. (eds.) ALT 1995. LNCS, vol. 997, pp. 80–94. Springer, Heidelberg (1995)Google Scholar
  13. 13.
    Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P.: From Data Mining to Knowledge Discovery: An Overview. In: Fayyad, U.M., Piatetsky-Shapiro, G., Smyth, P., Uthurusamy, R. (eds.) Advances in Knowledge Discovery and Data Mining, pp. 3–33. AAAI Press, Menlo Park (1996)Google Scholar
  14. 14.
    Férré, S., Ridoux, O.: A Logical Generalization of Formal Concept Analysis. In: Ganter, B., Mineau, G.W. (eds.) ICCS 2000. LNCS (LNAI), vol. 1867, Springer, Heidelberg (2000)Google Scholar
  15. 15.
    Férré, S., Ridoux, O.: The Use of Associative Concepts in the Incremental Building of a Logical Context. In: Priss, U., Corbett, D.R., Angelova, G. (eds.) ICCS 2002. LNCS (LNAI), vol. 2393, pp. 299–313. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  16. 16.
    Finn, V.K.: On Machine-Oriented Formalization of Plausible Reasoning in the Style of F. Backon–J. S. Mill. Semiotika Informatika 20, 35–101 (1983) (in Russian)MATHMathSciNetGoogle Scholar
  17. 17.
    Finn, V.K.: Plausible Reasoning in Systems of JSM Type, Itogi Nauki i Tekhniki. Seriya Informatika 15, 54–101 (1991) (in Russian)Google Scholar
  18. 18.
    Ganascia, J.G.: CHARADE: A rule system learning system. In: Proc. of the 10th International Joint Conference on Artificial Intelligence (IJCAI 1987), Milan, Italy, August 23-28, pp. 345–347 (1987)Google Scholar
  19. 19.
    Ganter, B., Kuznetsov, S.: Formalizing Hypotheses with Concepts. In: Ganter, B., Mineau, G.W. (eds.) ICCS 2000. LNCS (LNAI), vol. 1867, pp. 342–356. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  20. 20.
    Ganter, B., Kuznetsov, S.: Pattern Structures and Their Projections, Proc. 9th Int. Conf. on Conceptual Structures. In: Delugach, H.S., Stumme, G. (eds.) ICCS 2001. LNCS (LNAI), vol. 2120, pp. 129–142. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  21. 21.
    Ganter, B., Kuznetsov, S.O.: Hypotheses and Version Spaces. In: Ganter, B., de Moor, A., Lex, W. (eds.) ICCS 2003. LNCS, vol. 2746, pp. 83–95. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  22. 22.
    Ganter, B., Reuter, K.: Finding all closed sets: a general approach. Order 8, 283–290 (1991)MATHCrossRefMathSciNetGoogle Scholar
  23. 23.
    Ganter, B., Wille, R.: Formal Concept Analysis: Mathematical Foundations. Springer, Heidelberg (1999)MATHGoogle Scholar
  24. 24.
    Garey, M., Johnson, D.: Computers and Intractability: A Guide to the Theory of NP-Completeness. Freeman, New York (1979)MATHGoogle Scholar
  25. 25.
    Grigoriev, P.A., Yevtushenko, S.A.: Elements of an Agile Discovery Environment. In: Grieser, G., Tanaka, Y., Yamamoto, A. (eds.) DS 2003. LNCS (LNAI), vol. 2843, pp. 309–316. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  26. 26.
    Grigoriev, P.A., Yevtushenko, S.A., Grieser, G.: QuDA, a data miner’s discovery enviornment, Tehcnical Report AIDA 03 06, FG Intellektik, FB Informatik, Technische Universitaet Darmstadt (September 2003), http://www.intellektik.informatik.tu-darmstadt.de/peter/QuDA.pdf
  27. 27.
    Gunter, C.A., Ngair, T.-H., Subramanian, D.: The Common Order-Theoretic Structure of Version Spaces and ATMSs. Artificial Intelligence 95, 357–407 (1997)MATHCrossRefMathSciNetGoogle Scholar
  28. 28.
    Helma, C., King, R.D., Kramer, S., Srinvasan, A.: Proc. of the Workshop on Predictive Toxicology Challegnge at the 5th Conference on Data Mining and Knowledge Discovery (PKDD 2001), Freiburg, Germany, September 7 (2001), http://www.predictive-toxicology.org/ptc/
  29. 29.
    Hereth, J., Stumme, G., Wille, R., Wille, U.: Conceptual Knowledge Discovery and Data Analysis. In: Ganter, B., Mineau, G.W. (eds.) ICCS 2000. LNCS (LNAI), vol. 1867, pp. 421–437. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  30. 30.
    Hirsh, H.: Generalizing Version Spaces. Machine Learning 17, 5–46 (1994)MATHGoogle Scholar
  31. 31.
    Hirsh, H., Mishra, N., Pitt, L.: Version Spaces Without Boundary Sets. In: Proc. of the 14th National Conference on Artificial Intelligence (AAAI 1997), AAAI Press/MIT Press (1997)Google Scholar
  32. 32.
    King, R.D., Srinivasan, A., Dehaspe, L.: WARMR: A Data Mining tool for chemical data. J. Computer-Aided Molecular Design 15, 173–181 (2001)CrossRefGoogle Scholar
  33. 33.
    Kramer, S.: Structural Regression Trees. In: Proc. 13th National Conference on Artificial Intelligence (AAAI 1996), pp. 812–819. AAAI Press, Menlo Park (1996)Google Scholar
  34. 34.
    Kuznetsov, S.O.: Interpretation on Graphs and Complexity Characteristics of a Search for Specific Patterns. Nauchn. Tekh. Inf., Ser. 2 (Automat. Document. Math. Linguist.) (1), 23–27 (1989)Google Scholar
  35. 35.
    Kuznetsov, S.O.: JSM-method as a machine learning method. Itogi Nauki i Tekhniki, ser. Informatika 15, 17–50 (1991) (in Russian)Google Scholar
  36. 36.
    Kuznetsov, S.O., Finn, V.K.: On a model of learning and classification based on similarity operation. Obozrenie Prikladnoi i Promyshlennoi Matematiki 3(1), 66–90 (1996) (in Russian)MATHGoogle Scholar
  37. 37.
    Kuznetsov, S.O.: Learning of Simple Conceptual Graphs from Positive and Negative Examples. In: Żytkow, J.M., Rauch, J. (eds.) PKDD 1999. LNCS (LNAI), vol. 1704, pp. 384–392. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  38. 38.
    Kuznetsov, S.O.: On Computing the Size of a Lattice and Related Decision Problems. Order 18(4), 313–321 (2001)MATHCrossRefMathSciNetGoogle Scholar
  39. 39.
    Kuznetsov, S.O., Obiedkov, S.A.: Comparing performance of algorithms for generating concept lattices. J. Exp. Theor. Artif. Intell. 14(2-3), 189–216 (2002)MATHCrossRefGoogle Scholar
  40. 40.
    Liquiere, M., Sallantin, J.: Structural Machine Learning with Galois Lattice and Graphs. In: Proc. Int. Conf. Machine Learning ICML 1998 (1998)Google Scholar
  41. 41.
    Maier, D.: The Theory of Relational Databases. Comput. Sci. Press, Potomac (1983)MATHGoogle Scholar
  42. 42.
    Luxenburger, M.: Implications partielle dans un contexte. Math. Sci. Hum. (1991)Google Scholar
  43. 43.
    Njiwoua, P., Mefu Nguifo, E.: Forwarding the choice of bias. LEGAL-F: Using Feature Selection to Reduce Complexity of LEGAL. In: Proc. of BENELEARN 1997, pp. 89–98 (1997)Google Scholar
  44. 44.
    Mitchell, T.: Version Space: An Approach to Concept Learning, PhD thesis, Stanford University (1978)Google Scholar
  45. 45.
    Mitchell, T.: Generalization as Search. Artificial Intelligence 18(2) (1982)Google Scholar
  46. 46.
    Mitchell, T.: Machine Learning. The McGraw-Hill Companies, New York (1997)MATHGoogle Scholar
  47. 47.
    Muggleton, S.: Inverse Entailment and Progol, New Generation Computing. Special Issue on Inductive Logic Programming 13(3-4), 245–286 (1995)Google Scholar
  48. 48.
    Nienhuys-Cheng, S.-H., de Wolf, R.: Foundations of Inductive Logic Programming. LNCS, vol. 1228. Springer, Heidelberg (1997)Google Scholar
  49. 49.
    Oosthuizen, G.D., McGregor, D.R.: Induction Through Knowledge Normalization. In: Proc. 8th. European Conference on Artificial Intelligence, Munich (1988)Google Scholar
  50. 50.
    Oosthuizen, G.D.: The use of of a lattice in Knowledge Processing, PhD Thesis, University of Strathclyde, Glasgow (1988)Google Scholar
  51. 51.
    Oosthuizen, G.D.: The application of Concept Lattices to Machine Learning, Univeristy of Pretoria, Tech. Rep. CSTR 94/01 (1994)Google Scholar
  52. 52.
    Pasquier, N., Bastide, Y., Taouil, R., Lakhal, L.: Efficient Minining of Association Rules Based on Using Closed Itemset Lattices. J. Inf. Systems 24, 25–46 (1999)CrossRefGoogle Scholar
  53. 53.
    Popov, D.V., Blinova, V.G., Pankratova, E.S.: Drug deisgn. JSM-Method of hypothesis generation for predicting antitumor activity and toxic effects forecasts with respect to plant products. In: Proc. 5th Int. Conf. on Chemistry and Biotechnology of Biologically Active Natural Products, Varna (Bulgaria), September 18-23, vol. 2, pp. 437–440 (1989)Google Scholar
  54. 54.
    Quinlan, J.R.: Induction on Decision Trees. Machine Learning 1(1), 81–106 (1986)Google Scholar
  55. 55.
    Sahami, M.: Learning Classification Rules Using Lattices. In: Lavrac, N., Wrobel, S. (eds.) ECML 1995. LNCS, vol. 912, pp. 343–346. Springer, Heidelberg (1995)Google Scholar
  56. 56.
    Sebag, M.: Using Constraints to Building Version Spaces. In: de Raedt, L., Bergadano, F. (eds.) ECML 1994. LNCS, vol. 784, pp. 257–271. Springer, Heidelberg (1994)Google Scholar
  57. 57.
    Sebag, M.: Delaying the Choice of Bias: A Disjunctive Version Space Approach. In: Saitta, L. (ed.) Proc. of the 13th International Conference on Machine Learning, pp. 444–452. Morgan Kaufmann, San Francisco (1996)Google Scholar
  58. 58.
    Sebag, M., Rouveroil, C.: Tractable induction and classification in first-order logic via stochastic matching. In: Proc. 15th International Joint Conference on Artificial Intelligence, pp. 888–893. Morgan Kaufmann, San Francisco (1997)Google Scholar
  59. 59.
    Smirnov, E.N., Braspenning, P.J.: Version Space Learning with Instance-Based Boundary Sets. In: Prade, H. (ed.) Proc. of 13th European Conference on Artificial Intelligence, pp. 460–464. J. Wiley, Chichester (1998)Google Scholar
  60. 60.
    Srinivasan, S.H., Muggleton, M.J.E.: Theories for mutagenicity: a study in first order and feature-based induction. Artificial Intelligence 85, 277–299 (1996)CrossRefGoogle Scholar
  61. 61.
    Stumme, G., Wille, R., Wille, U.: Conceptual Knowledge Discovery in Databases Using Formal Concept Analysis Methods. In: Żytkow, J.M. (ed.) PKDD 1998. LNCS (LNAI), vol. 1510, pp. 450–458. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  62. 62.
    Wille, R.: Restructuring Lattice Theory: an Approach Based on Hierarchies of Concepts. In: Rival, I. (ed.) Ordered Sets, pp. 445–470. Reidel, Dordrecht (1982)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Sergei O. Kuznetsov
    • 1
  1. 1.All-Russian Institute for Scientific and Technical InformationTechnische Universität Dresden 

Personalised recommendations